Upload Date | July 15 2024 03:22 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
Model | iPad14,4 |
Model ID | iPad14,4 |
Motherboard | J618AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 7.33 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
3378
632.1 IPS |
|
Image Classification (F16)
|
100% |
3427
641.3 IPS |
|
Image Classification (I8)
|
99% |
3057
572.0 IPS |
|
Image Segmentation (F32)
|
100% |
1446
24.2 IPS |
|
Image Segmentation (F16)
|
100% |
1535
25.6 IPS |
|
Image Segmentation (I8)
|
100% |
1539
25.7 IPS |
|
Pose Estimation (F32)
|
100% |
23529
28.5 IPS |
|
Pose Estimation (F16)
|
100% |
24978
30.2 IPS |
|
Pose Estimation (I8)
|
100% |
24411
29.6 IPS |
|
Object Detection (F32)
|
100% |
2840
212.0 IPS |
|
Object Detection (F16)
|
100% |
2846
212.5 IPS |
|
Object Detection (I8)
|
97% |
2589
193.3 IPS |
|
Face Detection (F32)
|
100% |
9306
110.7 IPS |
|
Face Detection (F16)
|
98% |
10562
125.6 IPS |
|
Face Detection (I8)
|
97% |
10101
120.1 IPS |
|
Depth Estimation (F32)
|
100% |
16393
127.1 IPS |
|
Depth Estimation (F16)
|
100% |
17456
135.4 IPS |
|
Depth Estimation (I8)
|
37% |
16129
125.1 IPS |
|
Style Transfer (F32)
|
100% |
37662
49.5 IPS |
|
Style Transfer (F16)
|
100% |
46888
61.7 IPS |
|
Style Transfer (I8)
|
100% |
43300
57.0 IPS |
|
Image Super-Resolution (F32)
|
100% |
9406
335.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
10192
364.0 IPS |
|
Image Super-Resolution (I8)
|
100% |
9769
348.9 IPS |
|
Text Classification (F32)
|
100% |
1121
1.61 KIPS |
|
Text Classification (F16)
|
100% |
744
1.07 KIPS |
|
Text Classification (I8)
|
96% |
744
1.07 KIPS |
|
Machine Translation (F32)
|
100% |
806
14.8 IPS |
|
Machine Translation (F16)
|
100% |
810
14.9 IPS |
|
Machine Translation (I8)
|
99% |
743
13.7 IPS |